1// SPDX-License-Identifier: GPL-2.0-only
2/****************************************************************************
3 * Driver for Solarflare network controllers and boards
4 * Copyright 2010-2012 Solarflare Communications Inc.
5 */
6#include <linux/pci.h>
7#include <linux/module.h>
8#include "net_driver.h"
9#include "efx.h"
10#include "efx_channels.h"
11#include "nic.h"
12#include "io.h"
13#include "mcdi.h"
14#include "filter.h"
15#include "mcdi_pcol.h"
16#include "farch_regs.h"
17#include "siena_sriov.h"
18#include "vfdi.h"
19
20/* Number of longs required to track all the VIs in a VF */
21#define VI_MASK_LENGTH BITS_TO_LONGS(1 << EFX_VI_SCALE_MAX)
22
23/* Maximum number of RX queues supported */
24#define VF_MAX_RX_QUEUES 63
25
26/**
27 * enum efx_vf_tx_filter_mode - TX MAC filtering behaviour
28 * @VF_TX_FILTER_OFF: Disabled
29 * @VF_TX_FILTER_AUTO: Enabled if MAC address assigned to VF and only
30 *	2 TX queues allowed per VF.
31 * @VF_TX_FILTER_ON: Enabled
32 */
33enum efx_vf_tx_filter_mode {
34	VF_TX_FILTER_OFF,
35	VF_TX_FILTER_AUTO,
36	VF_TX_FILTER_ON,
37};
38
39/**
40 * struct siena_vf - Back-end resource and protocol state for a PCI VF
41 * @efx: The Efx NIC owning this VF
42 * @pci_rid: The PCI requester ID for this VF
43 * @pci_name: The PCI name (formatted address) of this VF
44 * @index: Index of VF within its port and PF.
45 * @req: VFDI incoming request work item. Incoming USR_EV events are received
46 *	by the NAPI handler, but must be handled by executing MCDI requests
47 *	inside a work item.
48 * @req_addr: VFDI incoming request DMA address (in VF's PCI address space).
49 * @req_type: Expected next incoming (from VF) %VFDI_EV_TYPE member.
50 * @req_seqno: Expected next incoming (from VF) %VFDI_EV_SEQ member.
51 * @msg_seqno: Next %VFDI_EV_SEQ member to reply to VF. Protected by
52 *	@status_lock
53 * @busy: VFDI request queued to be processed or being processed. Receiving
54 *	a VFDI request when @busy is set is an error condition.
55 * @buf: Incoming VFDI requests are DMA from the VF into this buffer.
56 * @buftbl_base: Buffer table entries for this VF start at this index.
57 * @rx_filtering: Receive filtering has been requested by the VF driver.
58 * @rx_filter_flags: The flags sent in the %VFDI_OP_INSERT_FILTER request.
59 * @rx_filter_qid: VF relative qid for RX filter requested by VF.
60 * @rx_filter_id: Receive MAC filter ID. Only one filter per VF is supported.
61 * @tx_filter_mode: Transmit MAC filtering mode.
62 * @tx_filter_id: Transmit MAC filter ID.
63 * @addr: The MAC address and outer vlan tag of the VF.
64 * @status_addr: VF DMA address of page for &struct vfdi_status updates.
65 * @status_lock: Mutex protecting @msg_seqno, @status_addr, @addr,
66 *	@peer_page_addrs and @peer_page_count from simultaneous
67 *	updates by the VM and consumption by
68 *	efx_siena_sriov_update_vf_addr()
69 * @peer_page_addrs: Pointer to an array of guest pages for local addresses.
70 * @peer_page_count: Number of entries in @peer_page_count.
71 * @evq0_addrs: Array of guest pages backing evq0.
72 * @evq0_count: Number of entries in @evq0_addrs.
73 * @flush_waitq: wait queue used by %VFDI_OP_FINI_ALL_QUEUES handler
74 *	to wait for flush completions.
75 * @txq_lock: Mutex for TX queue allocation.
76 * @txq_mask: Mask of initialized transmit queues.
77 * @txq_count: Number of initialized transmit queues.
78 * @rxq_mask: Mask of initialized receive queues.
79 * @rxq_count: Number of initialized receive queues.
80 * @rxq_retry_mask: Mask or receive queues that need to be flushed again
81 *	due to flush failure.
82 * @rxq_retry_count: Number of receive queues in @rxq_retry_mask.
83 * @reset_work: Work item to schedule a VF reset.
84 */
85struct siena_vf {
86	struct efx_nic *efx;
87	unsigned int pci_rid;
88	char pci_name[13]; /* dddd:bb:dd.f */
89	unsigned int index;
90	struct work_struct req;
91	u64 req_addr;
92	int req_type;
93	unsigned req_seqno;
94	unsigned msg_seqno;
95	bool busy;
96	struct efx_buffer buf;
97	unsigned buftbl_base;
98	bool rx_filtering;
99	enum efx_filter_flags rx_filter_flags;
100	unsigned rx_filter_qid;
101	int rx_filter_id;
102	enum efx_vf_tx_filter_mode tx_filter_mode;
103	int tx_filter_id;
104	struct vfdi_endpoint addr;
105	u64 status_addr;
106	struct mutex status_lock;
107	u64 *peer_page_addrs;
108	unsigned peer_page_count;
109	u64 evq0_addrs[EFX_MAX_VF_EVQ_SIZE * sizeof(efx_qword_t) /
110		       EFX_BUF_SIZE];
111	unsigned evq0_count;
112	wait_queue_head_t flush_waitq;
113	struct mutex txq_lock;
114	unsigned long txq_mask[VI_MASK_LENGTH];
115	unsigned txq_count;
116	unsigned long rxq_mask[VI_MASK_LENGTH];
117	unsigned rxq_count;
118	unsigned long rxq_retry_mask[VI_MASK_LENGTH];
119	atomic_t rxq_retry_count;
120	struct work_struct reset_work;
121};
122
123struct efx_memcpy_req {
124	unsigned int from_rid;
125	void *from_buf;
126	u64 from_addr;
127	unsigned int to_rid;
128	u64 to_addr;
129	unsigned length;
130};
131
132/**
133 * struct efx_local_addr - A MAC address on the vswitch without a VF.
134 *
135 * Siena does not have a switch, so VFs can't transmit data to each
136 * other. Instead the VFs must be made aware of the local addresses
137 * on the vswitch, so that they can arrange for an alternative
138 * software datapath to be used.
139 *
140 * @link: List head for insertion into efx->local_addr_list.
141 * @addr: Ethernet address
142 */
143struct efx_local_addr {
144	struct list_head link;
145	u8 addr[ETH_ALEN];
146};
147
148/**
149 * struct efx_endpoint_page - Page of vfdi_endpoint structures
150 *
151 * @link: List head for insertion into efx->local_page_list.
152 * @ptr: Pointer to page.
153 * @addr: DMA address of page.
154 */
155struct efx_endpoint_page {
156	struct list_head link;
157	void *ptr;
158	dma_addr_t addr;
159};
160
161/* Buffer table entries are reserved txq0,rxq0,evq0,txq1,rxq1,evq1 */
162#define EFX_BUFTBL_TXQ_BASE(_vf, _qid)					\
163	((_vf)->buftbl_base + EFX_VF_BUFTBL_PER_VI * (_qid))
164#define EFX_BUFTBL_RXQ_BASE(_vf, _qid)					\
165	(EFX_BUFTBL_TXQ_BASE(_vf, _qid) +				\
166	 (EFX_MAX_DMAQ_SIZE * sizeof(efx_qword_t) / EFX_BUF_SIZE))
167#define EFX_BUFTBL_EVQ_BASE(_vf, _qid)					\
168	(EFX_BUFTBL_TXQ_BASE(_vf, _qid) +				\
169	 (2 * EFX_MAX_DMAQ_SIZE * sizeof(efx_qword_t) / EFX_BUF_SIZE))
170
171#define EFX_FIELD_MASK(_field)			\
172	((1 << _field ## _WIDTH) - 1)
173
174/* VFs can only use this many transmit channels */
175static unsigned int vf_max_tx_channels = 2;
176module_param(vf_max_tx_channels, uint, 0444);
177MODULE_PARM_DESC(vf_max_tx_channels,
178		 "Limit the number of TX channels VFs can use");
179
180static int max_vfs = -1;
181module_param(max_vfs, int, 0444);
182MODULE_PARM_DESC(max_vfs,
183		 "Reduce the number of VFs initialized by the driver");
184
185/* Workqueue used by VFDI communication.  We can't use the global
186 * workqueue because it may be running the VF driver's probe()
187 * routine, which will be blocked there waiting for a VFDI response.
188 */
189static struct workqueue_struct *vfdi_workqueue;
190
191static unsigned abs_index(struct siena_vf *vf, unsigned index)
192{
193	return EFX_VI_BASE + vf->index * efx_vf_size(vf->efx) + index;
194}
195
196static int efx_siena_sriov_cmd(struct efx_nic *efx, bool enable,
197			       unsigned *vi_scale_out, unsigned *vf_total_out)
198{
199	MCDI_DECLARE_BUF(inbuf, MC_CMD_SRIOV_IN_LEN);
200	MCDI_DECLARE_BUF(outbuf, MC_CMD_SRIOV_OUT_LEN);
201	unsigned vi_scale, vf_total;
202	size_t outlen;
203	int rc;
204
205	MCDI_SET_DWORD(inbuf, SRIOV_IN_ENABLE, enable ? 1 : 0);
206	MCDI_SET_DWORD(inbuf, SRIOV_IN_VI_BASE, EFX_VI_BASE);
207	MCDI_SET_DWORD(inbuf, SRIOV_IN_VF_COUNT, efx->vf_count);
208
209	rc = efx_mcdi_rpc_quiet(efx, MC_CMD_SRIOV, inbuf, MC_CMD_SRIOV_IN_LEN,
210				outbuf, MC_CMD_SRIOV_OUT_LEN, &outlen);
211	if (rc)
212		return rc;
213	if (outlen < MC_CMD_SRIOV_OUT_LEN)
214		return -EIO;
215
216	vf_total = MCDI_DWORD(outbuf, SRIOV_OUT_VF_TOTAL);
217	vi_scale = MCDI_DWORD(outbuf, SRIOV_OUT_VI_SCALE);
218	if (vi_scale > EFX_VI_SCALE_MAX)
219		return -EOPNOTSUPP;
220
221	if (vi_scale_out)
222		*vi_scale_out = vi_scale;
223	if (vf_total_out)
224		*vf_total_out = vf_total;
225
226	return 0;
227}
228
229static void efx_siena_sriov_usrev(struct efx_nic *efx, bool enabled)
230{
231	struct siena_nic_data *nic_data = efx->nic_data;
232	efx_oword_t reg;
233
234	EFX_POPULATE_OWORD_2(reg,
235			     FRF_CZ_USREV_DIS, enabled ? 0 : 1,
236			     FRF_CZ_DFLT_EVQ, nic_data->vfdi_channel->channel);
237	efx_writeo(efx, &reg, FR_CZ_USR_EV_CFG);
238}
239
240static int efx_siena_sriov_memcpy(struct efx_nic *efx,
241				  struct efx_memcpy_req *req,
242				  unsigned int count)
243{
244	MCDI_DECLARE_BUF(inbuf, MCDI_CTL_SDU_LEN_MAX_V1);
245	MCDI_DECLARE_STRUCT_PTR(record);
246	unsigned int index, used;
247	u64 from_addr;
248	u32 from_rid;
249	int rc;
250
251	mb();	/* Finish writing source/reading dest before DMA starts */
252
253	if (WARN_ON(count > MC_CMD_MEMCPY_IN_RECORD_MAXNUM))
254		return -ENOBUFS;
255	used = MC_CMD_MEMCPY_IN_LEN(count);
256
257	for (index = 0; index < count; index++) {
258		record = MCDI_ARRAY_STRUCT_PTR(inbuf, MEMCPY_IN_RECORD, index);
259		MCDI_SET_DWORD(record, MEMCPY_RECORD_TYPEDEF_NUM_RECORDS,
260			       count);
261		MCDI_SET_DWORD(record, MEMCPY_RECORD_TYPEDEF_TO_RID,
262			       req->to_rid);
263		MCDI_SET_QWORD(record, MEMCPY_RECORD_TYPEDEF_TO_ADDR,
264			       req->to_addr);
265		if (req->from_buf == NULL) {
266			from_rid = req->from_rid;
267			from_addr = req->from_addr;
268		} else {
269			if (WARN_ON(used + req->length >
270				    MCDI_CTL_SDU_LEN_MAX_V1)) {
271				rc = -ENOBUFS;
272				goto out;
273			}
274
275			from_rid = MC_CMD_MEMCPY_RECORD_TYPEDEF_RID_INLINE;
276			from_addr = used;
277			memcpy(_MCDI_PTR(inbuf, used), req->from_buf,
278			       req->length);
279			used += req->length;
280		}
281
282		MCDI_SET_DWORD(record, MEMCPY_RECORD_TYPEDEF_FROM_RID, from_rid);
283		MCDI_SET_QWORD(record, MEMCPY_RECORD_TYPEDEF_FROM_ADDR,
284			       from_addr);
285		MCDI_SET_DWORD(record, MEMCPY_RECORD_TYPEDEF_LENGTH,
286			       req->length);
287
288		++req;
289	}
290
291	rc = efx_mcdi_rpc(efx, MC_CMD_MEMCPY, inbuf, used, NULL, 0, NULL);
292out:
293	mb();	/* Don't write source/read dest before DMA is complete */
294
295	return rc;
296}
297
298/* The TX filter is entirely controlled by this driver, and is modified
299 * underneath the feet of the VF
300 */
301static void efx_siena_sriov_reset_tx_filter(struct siena_vf *vf)
302{
303	struct efx_nic *efx = vf->efx;
304	struct efx_filter_spec filter;
305	u16 vlan;
306	int rc;
307
308	if (vf->tx_filter_id != -1) {
309		efx_filter_remove_id_safe(efx, EFX_FILTER_PRI_REQUIRED,
310					  vf->tx_filter_id);
311		netif_dbg(efx, hw, efx->net_dev, "Removed vf %s tx filter %d\n",
312			  vf->pci_name, vf->tx_filter_id);
313		vf->tx_filter_id = -1;
314	}
315
316	if (is_zero_ether_addr(vf->addr.mac_addr))
317		return;
318
319	/* Turn on TX filtering automatically if not explicitly
320	 * enabled or disabled.
321	 */
322	if (vf->tx_filter_mode == VF_TX_FILTER_AUTO && vf_max_tx_channels <= 2)
323		vf->tx_filter_mode = VF_TX_FILTER_ON;
324
325	vlan = ntohs(vf->addr.tci) & VLAN_VID_MASK;
326	efx_filter_init_tx(&filter, abs_index(vf, 0));
327	rc = efx_filter_set_eth_local(&filter,
328				      vlan ? vlan : EFX_FILTER_VID_UNSPEC,
329				      vf->addr.mac_addr);
330	BUG_ON(rc);
331
332	rc = efx_filter_insert_filter(efx, &filter, true);
333	if (rc < 0) {
334		netif_warn(efx, hw, efx->net_dev,
335			   "Unable to migrate tx filter for vf %s\n",
336			   vf->pci_name);
337	} else {
338		netif_dbg(efx, hw, efx->net_dev, "Inserted vf %s tx filter %d\n",
339			  vf->pci_name, rc);
340		vf->tx_filter_id = rc;
341	}
342}
343
344/* The RX filter is managed here on behalf of the VF driver */
345static void efx_siena_sriov_reset_rx_filter(struct siena_vf *vf)
346{
347	struct efx_nic *efx = vf->efx;
348	struct efx_filter_spec filter;
349	u16 vlan;
350	int rc;
351
352	if (vf->rx_filter_id != -1) {
353		efx_filter_remove_id_safe(efx, EFX_FILTER_PRI_REQUIRED,
354					  vf->rx_filter_id);
355		netif_dbg(efx, hw, efx->net_dev, "Removed vf %s rx filter %d\n",
356			  vf->pci_name, vf->rx_filter_id);
357		vf->rx_filter_id = -1;
358	}
359
360	if (!vf->rx_filtering || is_zero_ether_addr(vf->addr.mac_addr))
361		return;
362
363	vlan = ntohs(vf->addr.tci) & VLAN_VID_MASK;
364	efx_filter_init_rx(&filter, EFX_FILTER_PRI_REQUIRED,
365			   vf->rx_filter_flags,
366			   abs_index(vf, vf->rx_filter_qid));
367	rc = efx_filter_set_eth_local(&filter,
368				      vlan ? vlan : EFX_FILTER_VID_UNSPEC,
369				      vf->addr.mac_addr);
370	BUG_ON(rc);
371
372	rc = efx_filter_insert_filter(efx, &filter, true);
373	if (rc < 0) {
374		netif_warn(efx, hw, efx->net_dev,
375			   "Unable to insert rx filter for vf %s\n",
376			   vf->pci_name);
377	} else {
378		netif_dbg(efx, hw, efx->net_dev, "Inserted vf %s rx filter %d\n",
379			  vf->pci_name, rc);
380		vf->rx_filter_id = rc;
381	}
382}
383
384static void __efx_siena_sriov_update_vf_addr(struct siena_vf *vf)
385{
386	struct efx_nic *efx = vf->efx;
387	struct siena_nic_data *nic_data = efx->nic_data;
388
389	efx_siena_sriov_reset_tx_filter(vf);
390	efx_siena_sriov_reset_rx_filter(vf);
391	queue_work(vfdi_workqueue, &nic_data->peer_work);
392}
393
394/* Push the peer list to this VF. The caller must hold status_lock to interlock
395 * with VFDI requests, and they must be serialised against manipulation of
396 * local_page_list, either by acquiring local_lock or by running from
397 * efx_siena_sriov_peer_work()
398 */
399static void __efx_siena_sriov_push_vf_status(struct siena_vf *vf)
400{
401	struct efx_nic *efx = vf->efx;
402	struct siena_nic_data *nic_data = efx->nic_data;
403	struct vfdi_status *status = nic_data->vfdi_status.addr;
404	struct efx_memcpy_req copy[4];
405	struct efx_endpoint_page *epp;
406	unsigned int pos, count;
407	unsigned data_offset;
408	efx_qword_t event;
409
410	WARN_ON(!mutex_is_locked(&vf->status_lock));
411	WARN_ON(!vf->status_addr);
412
413	status->local = vf->addr;
414	status->generation_end = ++status->generation_start;
415
416	memset(copy, '\0', sizeof(copy));
417	/* Write generation_start */
418	copy[0].from_buf = &status->generation_start;
419	copy[0].to_rid = vf->pci_rid;
420	copy[0].to_addr = vf->status_addr + offsetof(struct vfdi_status,
421						     generation_start);
422	copy[0].length = sizeof(status->generation_start);
423	/* DMA the rest of the structure (excluding the generations). This
424	 * assumes that the non-generation portion of vfdi_status is in
425	 * one chunk starting at the version member.
426	 */
427	data_offset = offsetof(struct vfdi_status, version);
428	copy[1].from_rid = efx->pci_dev->devfn;
429	copy[1].from_addr = nic_data->vfdi_status.dma_addr + data_offset;
430	copy[1].to_rid = vf->pci_rid;
431	copy[1].to_addr = vf->status_addr + data_offset;
432	copy[1].length =  status->length - data_offset;
433
434	/* Copy the peer pages */
435	pos = 2;
436	count = 0;
437	list_for_each_entry(epp, &nic_data->local_page_list, link) {
438		if (count == vf->peer_page_count) {
439			/* The VF driver will know they need to provide more
440			 * pages because peer_addr_count is too large.
441			 */
442			break;
443		}
444		copy[pos].from_buf = NULL;
445		copy[pos].from_rid = efx->pci_dev->devfn;
446		copy[pos].from_addr = epp->addr;
447		copy[pos].to_rid = vf->pci_rid;
448		copy[pos].to_addr = vf->peer_page_addrs[count];
449		copy[pos].length = EFX_PAGE_SIZE;
450
451		if (++pos == ARRAY_SIZE(copy)) {
452			efx_siena_sriov_memcpy(efx, copy, ARRAY_SIZE(copy));
453			pos = 0;
454		}
455		++count;
456	}
457
458	/* Write generation_end */
459	copy[pos].from_buf = &status->generation_end;
460	copy[pos].to_rid = vf->pci_rid;
461	copy[pos].to_addr = vf->status_addr + offsetof(struct vfdi_status,
462						       generation_end);
463	copy[pos].length = sizeof(status->generation_end);
464	efx_siena_sriov_memcpy(efx, copy, pos + 1);
465
466	/* Notify the guest */
467	EFX_POPULATE_QWORD_3(event,
468			     FSF_AZ_EV_CODE, FSE_CZ_EV_CODE_USER_EV,
469			     VFDI_EV_SEQ, (vf->msg_seqno & 0xff),
470			     VFDI_EV_TYPE, VFDI_EV_TYPE_STATUS);
471	++vf->msg_seqno;
472	efx_farch_generate_event(efx,
473				 EFX_VI_BASE + vf->index * efx_vf_size(efx),
474				 &event);
475}
476
477static void efx_siena_sriov_bufs(struct efx_nic *efx, unsigned offset,
478				 u64 *addr, unsigned count)
479{
480	efx_qword_t buf;
481	unsigned pos;
482
483	for (pos = 0; pos < count; ++pos) {
484		EFX_POPULATE_QWORD_3(buf,
485				     FRF_AZ_BUF_ADR_REGION, 0,
486				     FRF_AZ_BUF_ADR_FBUF,
487				     addr ? addr[pos] >> 12 : 0,
488				     FRF_AZ_BUF_OWNER_ID_FBUF, 0);
489		efx_sram_writeq(efx, efx->membase + FR_BZ_BUF_FULL_TBL,
490				&buf, offset + pos);
491	}
492}
493
494static bool bad_vf_index(struct efx_nic *efx, unsigned index)
495{
496	return index >= efx_vf_size(efx);
497}
498
499static bool bad_buf_count(unsigned buf_count, unsigned max_entry_count)
500{
501	unsigned max_buf_count = max_entry_count *
502		sizeof(efx_qword_t) / EFX_BUF_SIZE;
503
504	return ((buf_count & (buf_count - 1)) || buf_count > max_buf_count);
505}
506
507/* Check that VI specified by per-port index belongs to a VF.
508 * Optionally set VF index and VI index within the VF.
509 */
510static bool map_vi_index(struct efx_nic *efx, unsigned abs_index,
511			 struct siena_vf **vf_out, unsigned *rel_index_out)
512{
513	struct siena_nic_data *nic_data = efx->nic_data;
514	unsigned vf_i;
515
516	if (abs_index < EFX_VI_BASE)
517		return true;
518	vf_i = (abs_index - EFX_VI_BASE) / efx_vf_size(efx);
519	if (vf_i >= efx->vf_init_count)
520		return true;
521
522	if (vf_out)
523		*vf_out = nic_data->vf + vf_i;
524	if (rel_index_out)
525		*rel_index_out = abs_index % efx_vf_size(efx);
526	return false;
527}
528
529static int efx_vfdi_init_evq(struct siena_vf *vf)
530{
531	struct efx_nic *efx = vf->efx;
532	struct vfdi_req *req = vf->buf.addr;
533	unsigned vf_evq = req->u.init_evq.index;
534	unsigned buf_count = req->u.init_evq.buf_count;
535	unsigned abs_evq = abs_index(vf, vf_evq);
536	unsigned buftbl = EFX_BUFTBL_EVQ_BASE(vf, vf_evq);
537	efx_oword_t reg;
538
539	if (bad_vf_index(efx, vf_evq) ||
540	    bad_buf_count(buf_count, EFX_MAX_VF_EVQ_SIZE)) {
541		if (net_ratelimit())
542			netif_err(efx, hw, efx->net_dev,
543				  "ERROR: Invalid INIT_EVQ from %s: evq %d bufs %d\n",
544				  vf->pci_name, vf_evq, buf_count);
545		return VFDI_RC_EINVAL;
546	}
547
548	efx_siena_sriov_bufs(efx, buftbl, req->u.init_evq.addr, buf_count);
549
550	EFX_POPULATE_OWORD_3(reg,
551			     FRF_CZ_TIMER_Q_EN, 1,
552			     FRF_CZ_HOST_NOTIFY_MODE, 0,
553			     FRF_CZ_TIMER_MODE, FFE_CZ_TIMER_MODE_DIS);
554	efx_writeo_table(efx, &reg, FR_BZ_TIMER_TBL, abs_evq);
555	EFX_POPULATE_OWORD_3(reg,
556			     FRF_AZ_EVQ_EN, 1,
557			     FRF_AZ_EVQ_SIZE, __ffs(buf_count),
558			     FRF_AZ_EVQ_BUF_BASE_ID, buftbl);
559	efx_writeo_table(efx, &reg, FR_BZ_EVQ_PTR_TBL, abs_evq);
560
561	if (vf_evq == 0) {
562		memcpy(vf->evq0_addrs, req->u.init_evq.addr,
563		       buf_count * sizeof(u64));
564		vf->evq0_count = buf_count;
565	}
566
567	return VFDI_RC_SUCCESS;
568}
569
570static int efx_vfdi_init_rxq(struct siena_vf *vf)
571{
572	struct efx_nic *efx = vf->efx;
573	struct vfdi_req *req = vf->buf.addr;
574	unsigned vf_rxq = req->u.init_rxq.index;
575	unsigned vf_evq = req->u.init_rxq.evq;
576	unsigned buf_count = req->u.init_rxq.buf_count;
577	unsigned buftbl = EFX_BUFTBL_RXQ_BASE(vf, vf_rxq);
578	unsigned label;
579	efx_oword_t reg;
580
581	if (bad_vf_index(efx, vf_evq) || bad_vf_index(efx, vf_rxq) ||
582	    vf_rxq >= VF_MAX_RX_QUEUES ||
583	    bad_buf_count(buf_count, EFX_MAX_DMAQ_SIZE)) {
584		if (net_ratelimit())
585			netif_err(efx, hw, efx->net_dev,
586				  "ERROR: Invalid INIT_RXQ from %s: rxq %d evq %d "
587				  "buf_count %d\n", vf->pci_name, vf_rxq,
588				  vf_evq, buf_count);
589		return VFDI_RC_EINVAL;
590	}
591	if (__test_and_set_bit(req->u.init_rxq.index, vf->rxq_mask))
592		++vf->rxq_count;
593	efx_siena_sriov_bufs(efx, buftbl, req->u.init_rxq.addr, buf_count);
594
595	label = req->u.init_rxq.label & EFX_FIELD_MASK(FRF_AZ_RX_DESCQ_LABEL);
596	EFX_POPULATE_OWORD_6(reg,
597			     FRF_AZ_RX_DESCQ_BUF_BASE_ID, buftbl,
598			     FRF_AZ_RX_DESCQ_EVQ_ID, abs_index(vf, vf_evq),
599			     FRF_AZ_RX_DESCQ_LABEL, label,
600			     FRF_AZ_RX_DESCQ_SIZE, __ffs(buf_count),
601			     FRF_AZ_RX_DESCQ_JUMBO,
602			     !!(req->u.init_rxq.flags &
603				VFDI_RXQ_FLAG_SCATTER_EN),
604			     FRF_AZ_RX_DESCQ_EN, 1);
605	efx_writeo_table(efx, &reg, FR_BZ_RX_DESC_PTR_TBL,
606			 abs_index(vf, vf_rxq));
607
608	return VFDI_RC_SUCCESS;
609}
610
611static int efx_vfdi_init_txq(struct siena_vf *vf)
612{
613	struct efx_nic *efx = vf->efx;
614	struct vfdi_req *req = vf->buf.addr;
615	unsigned vf_txq = req->u.init_txq.index;
616	unsigned vf_evq = req->u.init_txq.evq;
617	unsigned buf_count = req->u.init_txq.buf_count;
618	unsigned buftbl = EFX_BUFTBL_TXQ_BASE(vf, vf_txq);
619	unsigned label, eth_filt_en;
620	efx_oword_t reg;
621
622	if (bad_vf_index(efx, vf_evq) || bad_vf_index(efx, vf_txq) ||
623	    vf_txq >= vf_max_tx_channels ||
624	    bad_buf_count(buf_count, EFX_MAX_DMAQ_SIZE)) {
625		if (net_ratelimit())
626			netif_err(efx, hw, efx->net_dev,
627				  "ERROR: Invalid INIT_TXQ from %s: txq %d evq %d "
628				  "buf_count %d\n", vf->pci_name, vf_txq,
629				  vf_evq, buf_count);
630		return VFDI_RC_EINVAL;
631	}
632
633	mutex_lock(&vf->txq_lock);
634	if (__test_and_set_bit(req->u.init_txq.index, vf->txq_mask))
635		++vf->txq_count;
636	mutex_unlock(&vf->txq_lock);
637	efx_siena_sriov_bufs(efx, buftbl, req->u.init_txq.addr, buf_count);
638
639	eth_filt_en = vf->tx_filter_mode == VF_TX_FILTER_ON;
640
641	label = req->u.init_txq.label & EFX_FIELD_MASK(FRF_AZ_TX_DESCQ_LABEL);
642	EFX_POPULATE_OWORD_8(reg,
643			     FRF_CZ_TX_DPT_Q_MASK_WIDTH, min(efx->vi_scale, 1U),
644			     FRF_CZ_TX_DPT_ETH_FILT_EN, eth_filt_en,
645			     FRF_AZ_TX_DESCQ_EN, 1,
646			     FRF_AZ_TX_DESCQ_BUF_BASE_ID, buftbl,
647			     FRF_AZ_TX_DESCQ_EVQ_ID, abs_index(vf, vf_evq),
648			     FRF_AZ_TX_DESCQ_LABEL, label,
649			     FRF_AZ_TX_DESCQ_SIZE, __ffs(buf_count),
650			     FRF_BZ_TX_NON_IP_DROP_DIS, 1);
651	efx_writeo_table(efx, &reg, FR_BZ_TX_DESC_PTR_TBL,
652			 abs_index(vf, vf_txq));
653
654	return VFDI_RC_SUCCESS;
655}
656
657/* Returns true when efx_vfdi_fini_all_queues should wake */
658static bool efx_vfdi_flush_wake(struct siena_vf *vf)
659{
660	/* Ensure that all updates are visible to efx_vfdi_fini_all_queues() */
661	smp_mb();
662
663	return (!vf->txq_count && !vf->rxq_count) ||
664		atomic_read(&vf->rxq_retry_count);
665}
666
667static void efx_vfdi_flush_clear(struct siena_vf *vf)
668{
669	memset(vf->txq_mask, 0, sizeof(vf->txq_mask));
670	vf->txq_count = 0;
671	memset(vf->rxq_mask, 0, sizeof(vf->rxq_mask));
672	vf->rxq_count = 0;
673	memset(vf->rxq_retry_mask, 0, sizeof(vf->rxq_retry_mask));
674	atomic_set(&vf->rxq_retry_count, 0);
675}
676
677static int efx_vfdi_fini_all_queues(struct siena_vf *vf)
678{
679	struct efx_nic *efx = vf->efx;
680	efx_oword_t reg;
681	unsigned count = efx_vf_size(efx);
682	unsigned vf_offset = EFX_VI_BASE + vf->index * efx_vf_size(efx);
683	unsigned timeout = HZ;
684	unsigned index, rxqs_count;
685	MCDI_DECLARE_BUF(inbuf, MC_CMD_FLUSH_RX_QUEUES_IN_LENMAX);
686	int rc;
687
688	BUILD_BUG_ON(VF_MAX_RX_QUEUES >
689		     MC_CMD_FLUSH_RX_QUEUES_IN_QID_OFST_MAXNUM);
690
691	rtnl_lock();
692	siena_prepare_flush(efx);
693	rtnl_unlock();
694
695	/* Flush all the initialized queues */
696	rxqs_count = 0;
697	for (index = 0; index < count; ++index) {
698		if (test_bit(index, vf->txq_mask)) {
699			EFX_POPULATE_OWORD_2(reg,
700					     FRF_AZ_TX_FLUSH_DESCQ_CMD, 1,
701					     FRF_AZ_TX_FLUSH_DESCQ,
702					     vf_offset + index);
703			efx_writeo(efx, &reg, FR_AZ_TX_FLUSH_DESCQ);
704		}
705		if (test_bit(index, vf->rxq_mask)) {
706			MCDI_SET_ARRAY_DWORD(
707				inbuf, FLUSH_RX_QUEUES_IN_QID_OFST,
708				rxqs_count, vf_offset + index);
709			rxqs_count++;
710		}
711	}
712
713	atomic_set(&vf->rxq_retry_count, 0);
714	while (timeout && (vf->rxq_count || vf->txq_count)) {
715		rc = efx_mcdi_rpc(efx, MC_CMD_FLUSH_RX_QUEUES, inbuf,
716				  MC_CMD_FLUSH_RX_QUEUES_IN_LEN(rxqs_count),
717				  NULL, 0, NULL);
718		WARN_ON(rc < 0);
719
720		timeout = wait_event_timeout(vf->flush_waitq,
721					     efx_vfdi_flush_wake(vf),
722					     timeout);
723		rxqs_count = 0;
724		for (index = 0; index < count; ++index) {
725			if (test_and_clear_bit(index, vf->rxq_retry_mask)) {
726				atomic_dec(&vf->rxq_retry_count);
727				MCDI_SET_ARRAY_DWORD(
728					inbuf, FLUSH_RX_QUEUES_IN_QID_OFST,
729					rxqs_count, vf_offset + index);
730				rxqs_count++;
731			}
732		}
733	}
734
735	rtnl_lock();
736	siena_finish_flush(efx);
737	rtnl_unlock();
738
739	/* Irrespective of success/failure, fini the queues */
740	EFX_ZERO_OWORD(reg);
741	for (index = 0; index < count; ++index) {
742		efx_writeo_table(efx, &reg, FR_BZ_RX_DESC_PTR_TBL,
743				 vf_offset + index);
744		efx_writeo_table(efx, &reg, FR_BZ_TX_DESC_PTR_TBL,
745				 vf_offset + index);
746		efx_writeo_table(efx, &reg, FR_BZ_EVQ_PTR_TBL,
747				 vf_offset + index);
748		efx_writeo_table(efx, &reg, FR_BZ_TIMER_TBL,
749				 vf_offset + index);
750	}
751	efx_siena_sriov_bufs(efx, vf->buftbl_base, NULL,
752			     EFX_VF_BUFTBL_PER_VI * efx_vf_size(efx));
753	efx_vfdi_flush_clear(vf);
754
755	vf->evq0_count = 0;
756
757	return timeout ? 0 : VFDI_RC_ETIMEDOUT;
758}
759
760static int efx_vfdi_insert_filter(struct siena_vf *vf)
761{
762	struct efx_nic *efx = vf->efx;
763	struct siena_nic_data *nic_data = efx->nic_data;
764	struct vfdi_req *req = vf->buf.addr;
765	unsigned vf_rxq = req->u.mac_filter.rxq;
766	unsigned flags;
767
768	if (bad_vf_index(efx, vf_rxq) || vf->rx_filtering) {
769		if (net_ratelimit())
770			netif_err(efx, hw, efx->net_dev,
771				  "ERROR: Invalid INSERT_FILTER from %s: rxq %d "
772				  "flags 0x%x\n", vf->pci_name, vf_rxq,
773				  req->u.mac_filter.flags);
774		return VFDI_RC_EINVAL;
775	}
776
777	flags = 0;
778	if (req->u.mac_filter.flags & VFDI_MAC_FILTER_FLAG_RSS)
779		flags |= EFX_FILTER_FLAG_RX_RSS;
780	if (req->u.mac_filter.flags & VFDI_MAC_FILTER_FLAG_SCATTER)
781		flags |= EFX_FILTER_FLAG_RX_SCATTER;
782	vf->rx_filter_flags = flags;
783	vf->rx_filter_qid = vf_rxq;
784	vf->rx_filtering = true;
785
786	efx_siena_sriov_reset_rx_filter(vf);
787	queue_work(vfdi_workqueue, &nic_data->peer_work);
788
789	return VFDI_RC_SUCCESS;
790}
791
792static int efx_vfdi_remove_all_filters(struct siena_vf *vf)
793{
794	struct efx_nic *efx = vf->efx;
795	struct siena_nic_data *nic_data = efx->nic_data;
796
797	vf->rx_filtering = false;
798	efx_siena_sriov_reset_rx_filter(vf);
799	queue_work(vfdi_workqueue, &nic_data->peer_work);
800
801	return VFDI_RC_SUCCESS;
802}
803
804static int efx_vfdi_set_status_page(struct siena_vf *vf)
805{
806	struct efx_nic *efx = vf->efx;
807	struct siena_nic_data *nic_data = efx->nic_data;
808	struct vfdi_req *req = vf->buf.addr;
809	u64 page_count = req->u.set_status_page.peer_page_count;
810	u64 max_page_count =
811		(EFX_PAGE_SIZE -
812		 offsetof(struct vfdi_req, u.set_status_page.peer_page_addr[0]))
813		/ sizeof(req->u.set_status_page.peer_page_addr[0]);
814
815	if (!req->u.set_status_page.dma_addr || page_count > max_page_count) {
816		if (net_ratelimit())
817			netif_err(efx, hw, efx->net_dev,
818				  "ERROR: Invalid SET_STATUS_PAGE from %s\n",
819				  vf->pci_name);
820		return VFDI_RC_EINVAL;
821	}
822
823	mutex_lock(&nic_data->local_lock);
824	mutex_lock(&vf->status_lock);
825	vf->status_addr = req->u.set_status_page.dma_addr;
826
827	kfree(vf->peer_page_addrs);
828	vf->peer_page_addrs = NULL;
829	vf->peer_page_count = 0;
830
831	if (page_count) {
832		vf->peer_page_addrs = kcalloc(page_count, sizeof(u64),
833					      GFP_KERNEL);
834		if (vf->peer_page_addrs) {
835			memcpy(vf->peer_page_addrs,
836			       req->u.set_status_page.peer_page_addr,
837			       page_count * sizeof(u64));
838			vf->peer_page_count = page_count;
839		}
840	}
841
842	__efx_siena_sriov_push_vf_status(vf);
843	mutex_unlock(&vf->status_lock);
844	mutex_unlock(&nic_data->local_lock);
845
846	return VFDI_RC_SUCCESS;
847}
848
849static int efx_vfdi_clear_status_page(struct siena_vf *vf)
850{
851	mutex_lock(&vf->status_lock);
852	vf->status_addr = 0;
853	mutex_unlock(&vf->status_lock);
854
855	return VFDI_RC_SUCCESS;
856}
857
858typedef int (*efx_vfdi_op_t)(struct siena_vf *vf);
859
860static const efx_vfdi_op_t vfdi_ops[VFDI_OP_LIMIT] = {
861	[VFDI_OP_INIT_EVQ] = efx_vfdi_init_evq,
862	[VFDI_OP_INIT_TXQ] = efx_vfdi_init_txq,
863	[VFDI_OP_INIT_RXQ] = efx_vfdi_init_rxq,
864	[VFDI_OP_FINI_ALL_QUEUES] = efx_vfdi_fini_all_queues,
865	[VFDI_OP_INSERT_FILTER] = efx_vfdi_insert_filter,
866	[VFDI_OP_REMOVE_ALL_FILTERS] = efx_vfdi_remove_all_filters,
867	[VFDI_OP_SET_STATUS_PAGE] = efx_vfdi_set_status_page,
868	[VFDI_OP_CLEAR_STATUS_PAGE] = efx_vfdi_clear_status_page,
869};
870
871static void efx_siena_sriov_vfdi(struct work_struct *work)
872{
873	struct siena_vf *vf = container_of(work, struct siena_vf, req);
874	struct efx_nic *efx = vf->efx;
875	struct vfdi_req *req = vf->buf.addr;
876	struct efx_memcpy_req copy[2];
877	int rc;
878
879	/* Copy this page into the local address space */
880	memset(copy, '\0', sizeof(copy));
881	copy[0].from_rid = vf->pci_rid;
882	copy[0].from_addr = vf->req_addr;
883	copy[0].to_rid = efx->pci_dev->devfn;
884	copy[0].to_addr = vf->buf.dma_addr;
885	copy[0].length = EFX_PAGE_SIZE;
886	rc = efx_siena_sriov_memcpy(efx, copy, 1);
887	if (rc) {
888		/* If we can't get the request, we can't reply to the caller */
889		if (net_ratelimit())
890			netif_err(efx, hw, efx->net_dev,
891				  "ERROR: Unable to fetch VFDI request from %s rc %d\n",
892				  vf->pci_name, -rc);
893		vf->busy = false;
894		return;
895	}
896
897	if (req->op < VFDI_OP_LIMIT && vfdi_ops[req->op] != NULL) {
898		rc = vfdi_ops[req->op](vf);
899		if (rc == 0) {
900			netif_dbg(efx, hw, efx->net_dev,
901				  "vfdi request %d from %s ok\n",
902				  req->op, vf->pci_name);
903		}
904	} else {
905		netif_dbg(efx, hw, efx->net_dev,
906			  "ERROR: Unrecognised request %d from VF %s addr "
907			  "%llx\n", req->op, vf->pci_name,
908			  (unsigned long long)vf->req_addr);
909		rc = VFDI_RC_EOPNOTSUPP;
910	}
911
912	/* Allow subsequent VF requests */
913	vf->busy = false;
914	smp_wmb();
915
916	/* Respond to the request */
917	req->rc = rc;
918	req->op = VFDI_OP_RESPONSE;
919
920	memset(copy, '\0', sizeof(copy));
921	copy[0].from_buf = &req->rc;
922	copy[0].to_rid = vf->pci_rid;
923	copy[0].to_addr = vf->req_addr + offsetof(struct vfdi_req, rc);
924	copy[0].length = sizeof(req->rc);
925	copy[1].from_buf = &req->op;
926	copy[1].to_rid = vf->pci_rid;
927	copy[1].to_addr = vf->req_addr + offsetof(struct vfdi_req, op);
928	copy[1].length = sizeof(req->op);
929
930	(void)efx_siena_sriov_memcpy(efx, copy, ARRAY_SIZE(copy));
931}
932
933
934
935/* After a reset the event queues inside the guests no longer exist. Fill the
936 * event ring in guest memory with VFDI reset events, then (re-initialise) the
937 * event queue to raise an interrupt. The guest driver will then recover.
938 */
939
940static void efx_siena_sriov_reset_vf(struct siena_vf *vf,
941				     struct efx_buffer *buffer)
942{
943	struct efx_nic *efx = vf->efx;
944	struct efx_memcpy_req copy_req[4];
945	efx_qword_t event;
946	unsigned int pos, count, k, buftbl, abs_evq;
947	efx_oword_t reg;
948	efx_dword_t ptr;
949	int rc;
950
951	BUG_ON(buffer->len != EFX_PAGE_SIZE);
952
953	if (!vf->evq0_count)
954		return;
955	BUG_ON(vf->evq0_count & (vf->evq0_count - 1));
956
957	mutex_lock(&vf->status_lock);
958	EFX_POPULATE_QWORD_3(event,
959			     FSF_AZ_EV_CODE, FSE_CZ_EV_CODE_USER_EV,
960			     VFDI_EV_SEQ, vf->msg_seqno,
961			     VFDI_EV_TYPE, VFDI_EV_TYPE_RESET);
962	vf->msg_seqno++;
963	for (pos = 0; pos < EFX_PAGE_SIZE; pos += sizeof(event))
964		memcpy(buffer->addr + pos, &event, sizeof(event));
965
966	for (pos = 0; pos < vf->evq0_count; pos += count) {
967		count = min_t(unsigned, vf->evq0_count - pos,
968			      ARRAY_SIZE(copy_req));
969		for (k = 0; k < count; k++) {
970			copy_req[k].from_buf = NULL;
971			copy_req[k].from_rid = efx->pci_dev->devfn;
972			copy_req[k].from_addr = buffer->dma_addr;
973			copy_req[k].to_rid = vf->pci_rid;
974			copy_req[k].to_addr = vf->evq0_addrs[pos + k];
975			copy_req[k].length = EFX_PAGE_SIZE;
976		}
977		rc = efx_siena_sriov_memcpy(efx, copy_req, count);
978		if (rc) {
979			if (net_ratelimit())
980				netif_err(efx, hw, efx->net_dev,
981					  "ERROR: Unable to notify %s of reset"
982					  ": %d\n", vf->pci_name, -rc);
983			break;
984		}
985	}
986
987	/* Reinitialise, arm and trigger evq0 */
988	abs_evq = abs_index(vf, 0);
989	buftbl = EFX_BUFTBL_EVQ_BASE(vf, 0);
990	efx_siena_sriov_bufs(efx, buftbl, vf->evq0_addrs, vf->evq0_count);
991
992	EFX_POPULATE_OWORD_3(reg,
993			     FRF_CZ_TIMER_Q_EN, 1,
994			     FRF_CZ_HOST_NOTIFY_MODE, 0,
995			     FRF_CZ_TIMER_MODE, FFE_CZ_TIMER_MODE_DIS);
996	efx_writeo_table(efx, &reg, FR_BZ_TIMER_TBL, abs_evq);
997	EFX_POPULATE_OWORD_3(reg,
998			     FRF_AZ_EVQ_EN, 1,
999			     FRF_AZ_EVQ_SIZE, __ffs(vf->evq0_count),
1000			     FRF_AZ_EVQ_BUF_BASE_ID, buftbl);
1001	efx_writeo_table(efx, &reg, FR_BZ_EVQ_PTR_TBL, abs_evq);
1002	EFX_POPULATE_DWORD_1(ptr, FRF_AZ_EVQ_RPTR, 0);
1003	efx_writed(efx, &ptr, FR_BZ_EVQ_RPTR + FR_BZ_EVQ_RPTR_STEP * abs_evq);
1004
1005	mutex_unlock(&vf->status_lock);
1006}
1007
1008static void efx_siena_sriov_reset_vf_work(struct work_struct *work)
1009{
1010	struct siena_vf *vf = container_of(work, struct siena_vf, req);
1011	struct efx_nic *efx = vf->efx;
1012	struct efx_buffer buf;
1013
1014	if (!efx_nic_alloc_buffer(efx, &buf, EFX_PAGE_SIZE, GFP_NOIO)) {
1015		efx_siena_sriov_reset_vf(vf, &buf);
1016		efx_nic_free_buffer(efx, &buf);
1017	}
1018}
1019
1020static void efx_siena_sriov_handle_no_channel(struct efx_nic *efx)
1021{
1022	netif_err(efx, drv, efx->net_dev,
1023		  "ERROR: IOV requires MSI-X and 1 additional interrupt"
1024		  "vector. IOV disabled\n");
1025	efx->vf_count = 0;
1026}
1027
1028static int efx_siena_sriov_probe_channel(struct efx_channel *channel)
1029{
1030	struct siena_nic_data *nic_data = channel->efx->nic_data;
1031	nic_data->vfdi_channel = channel;
1032
1033	return 0;
1034}
1035
1036static void
1037efx_siena_sriov_get_channel_name(struct efx_channel *channel,
1038				 char *buf, size_t len)
1039{
1040	snprintf(buf, len, "%s-iov", channel->efx->name);
1041}
1042
1043static const struct efx_channel_type efx_siena_sriov_channel_type = {
1044	.handle_no_channel	= efx_siena_sriov_handle_no_channel,
1045	.pre_probe		= efx_siena_sriov_probe_channel,
1046	.post_remove		= efx_channel_dummy_op_void,
1047	.get_name		= efx_siena_sriov_get_channel_name,
1048	/* no copy operation; channel must not be reallocated */
1049	.keep_eventq		= true,
1050};
1051
1052void efx_siena_sriov_probe(struct efx_nic *efx)
1053{
1054	unsigned count;
1055
1056	if (!max_vfs)
1057		return;
1058
1059	if (efx_siena_sriov_cmd(efx, false, &efx->vi_scale, &count)) {
1060		pci_info(efx->pci_dev, "no SR-IOV VFs probed\n");
1061		return;
1062	}
1063	if (count > 0 && count > max_vfs)
1064		count = max_vfs;
1065
1066	/* efx_nic_dimension_resources() will reduce vf_count as appopriate */
1067	efx->vf_count = count;
1068
1069	efx->extra_channel_type[EFX_EXTRA_CHANNEL_IOV] = &efx_siena_sriov_channel_type;
1070}
1071
1072/* Copy the list of individual addresses into the vfdi_status.peers
1073 * array and auxiliary pages, protected by %local_lock. Drop that lock
1074 * and then broadcast the address list to every VF.
1075 */
1076static void efx_siena_sriov_peer_work(struct work_struct *data)
1077{
1078	struct siena_nic_data *nic_data = container_of(data,
1079						       struct siena_nic_data,
1080						       peer_work);
1081	struct efx_nic *efx = nic_data->efx;
1082	struct vfdi_status *vfdi_status = nic_data->vfdi_status.addr;
1083	struct siena_vf *vf;
1084	struct efx_local_addr *local_addr;
1085	struct vfdi_endpoint *peer;
1086	struct efx_endpoint_page *epp;
1087	struct list_head pages;
1088	unsigned int peer_space;
1089	unsigned int peer_count;
1090	unsigned int pos;
1091
1092	mutex_lock(&nic_data->local_lock);
1093
1094	/* Move the existing peer pages off %local_page_list */
1095	INIT_LIST_HEAD(&pages);
1096	list_splice_tail_init(&nic_data->local_page_list, &pages);
1097
1098	/* Populate the VF addresses starting from entry 1 (entry 0 is
1099	 * the PF address)
1100	 */
1101	peer = vfdi_status->peers + 1;
1102	peer_space = ARRAY_SIZE(vfdi_status->peers) - 1;
1103	peer_count = 1;
1104	for (pos = 0; pos < efx->vf_count; ++pos) {
1105		vf = nic_data->vf + pos;
1106
1107		mutex_lock(&vf->status_lock);
1108		if (vf->rx_filtering && !is_zero_ether_addr(vf->addr.mac_addr)) {
1109			*peer++ = vf->addr;
1110			++peer_count;
1111			--peer_space;
1112			BUG_ON(peer_space == 0);
1113		}
1114		mutex_unlock(&vf->status_lock);
1115	}
1116
1117	/* Fill the remaining addresses */
1118	list_for_each_entry(local_addr, &nic_data->local_addr_list, link) {
1119		ether_addr_copy(peer->mac_addr, local_addr->addr);
1120		peer->tci = 0;
1121		++peer;
1122		++peer_count;
1123		if (--peer_space == 0) {
1124			if (list_empty(&pages)) {
1125				epp = kmalloc(sizeof(*epp), GFP_KERNEL);
1126				if (!epp)
1127					break;
1128				epp->ptr = dma_alloc_coherent(
1129					&efx->pci_dev->dev, EFX_PAGE_SIZE,
1130					&epp->addr, GFP_KERNEL);
1131				if (!epp->ptr) {
1132					kfree(epp);
1133					break;
1134				}
1135			} else {
1136				epp = list_first_entry(
1137					&pages, struct efx_endpoint_page, link);
1138				list_del(&epp->link);
1139			}
1140
1141			list_add_tail(&epp->link, &nic_data->local_page_list);
1142			peer = (struct vfdi_endpoint *)epp->ptr;
1143			peer_space = EFX_PAGE_SIZE / sizeof(struct vfdi_endpoint);
1144		}
1145	}
1146	vfdi_status->peer_count = peer_count;
1147	mutex_unlock(&nic_data->local_lock);
1148
1149	/* Free any now unused endpoint pages */
1150	while (!list_empty(&pages)) {
1151		epp = list_first_entry(
1152			&pages, struct efx_endpoint_page, link);
1153		list_del(&epp->link);
1154		dma_free_coherent(&efx->pci_dev->dev, EFX_PAGE_SIZE,
1155				  epp->ptr, epp->addr);
1156		kfree(epp);
1157	}
1158
1159	/* Finally, push the pages */
1160	for (pos = 0; pos < efx->vf_count; ++pos) {
1161		vf = nic_data->vf + pos;
1162
1163		mutex_lock(&vf->status_lock);
1164		if (vf->status_addr)
1165			__efx_siena_sriov_push_vf_status(vf);
1166		mutex_unlock(&vf->status_lock);
1167	}
1168}
1169
1170static void efx_siena_sriov_free_local(struct efx_nic *efx)
1171{
1172	struct siena_nic_data *nic_data = efx->nic_data;
1173	struct efx_local_addr *local_addr;
1174	struct efx_endpoint_page *epp;
1175
1176	while (!list_empty(&nic_data->local_addr_list)) {
1177		local_addr = list_first_entry(&nic_data->local_addr_list,
1178					      struct efx_local_addr, link);
1179		list_del(&local_addr->link);
1180		kfree(local_addr);
1181	}
1182
1183	while (!list_empty(&nic_data->local_page_list)) {
1184		epp = list_first_entry(&nic_data->local_page_list,
1185				       struct efx_endpoint_page, link);
1186		list_del(&epp->link);
1187		dma_free_coherent(&efx->pci_dev->dev, EFX_PAGE_SIZE,
1188				  epp->ptr, epp->addr);
1189		kfree(epp);
1190	}
1191}
1192
1193static int efx_siena_sriov_vf_alloc(struct efx_nic *efx)
1194{
1195	unsigned index;
1196	struct siena_vf *vf;
1197	struct siena_nic_data *nic_data = efx->nic_data;
1198
1199	nic_data->vf = kcalloc(efx->vf_count, sizeof(*nic_data->vf),
1200			       GFP_KERNEL);
1201	if (!nic_data->vf)
1202		return -ENOMEM;
1203
1204	for (index = 0; index < efx->vf_count; ++index) {
1205		vf = nic_data->vf + index;
1206
1207		vf->efx = efx;
1208		vf->index = index;
1209		vf->rx_filter_id = -1;
1210		vf->tx_filter_mode = VF_TX_FILTER_AUTO;
1211		vf->tx_filter_id = -1;
1212		INIT_WORK(&vf->req, efx_siena_sriov_vfdi);
1213		INIT_WORK(&vf->reset_work, efx_siena_sriov_reset_vf_work);
1214		init_waitqueue_head(&vf->flush_waitq);
1215		mutex_init(&vf->status_lock);
1216		mutex_init(&vf->txq_lock);
1217	}
1218
1219	return 0;
1220}
1221
1222static void efx_siena_sriov_vfs_fini(struct efx_nic *efx)
1223{
1224	struct siena_nic_data *nic_data = efx->nic_data;
1225	struct siena_vf *vf;
1226	unsigned int pos;
1227
1228	for (pos = 0; pos < efx->vf_count; ++pos) {
1229		vf = nic_data->vf + pos;
1230
1231		efx_nic_free_buffer(efx, &vf->buf);
1232		kfree(vf->peer_page_addrs);
1233		vf->peer_page_addrs = NULL;
1234		vf->peer_page_count = 0;
1235
1236		vf->evq0_count = 0;
1237	}
1238}
1239
1240static int efx_siena_sriov_vfs_init(struct efx_nic *efx)
1241{
1242	struct pci_dev *pci_dev = efx->pci_dev;
1243	struct siena_nic_data *nic_data = efx->nic_data;
1244	unsigned index, devfn, sriov, buftbl_base;
1245	u16 offset, stride;
1246	struct siena_vf *vf;
1247	int rc;
1248
1249	sriov = pci_find_ext_capability(pci_dev, PCI_EXT_CAP_ID_SRIOV);
1250	if (!sriov)
1251		return -ENOENT;
1252
1253	pci_read_config_word(pci_dev, sriov + PCI_SRIOV_VF_OFFSET, &offset);
1254	pci_read_config_word(pci_dev, sriov + PCI_SRIOV_VF_STRIDE, &stride);
1255
1256	buftbl_base = nic_data->vf_buftbl_base;
1257	devfn = pci_dev->devfn + offset;
1258	for (index = 0; index < efx->vf_count; ++index) {
1259		vf = nic_data->vf + index;
1260
1261		/* Reserve buffer entries */
1262		vf->buftbl_base = buftbl_base;
1263		buftbl_base += EFX_VF_BUFTBL_PER_VI * efx_vf_size(efx);
1264
1265		vf->pci_rid = devfn;
1266		snprintf(vf->pci_name, sizeof(vf->pci_name),
1267			 "%04x:%02x:%02x.%d",
1268			 pci_domain_nr(pci_dev->bus), pci_dev->bus->number,
1269			 PCI_SLOT(devfn), PCI_FUNC(devfn));
1270
1271		rc = efx_nic_alloc_buffer(efx, &vf->buf, EFX_PAGE_SIZE,
1272					  GFP_KERNEL);
1273		if (rc)
1274			goto fail;
1275
1276		devfn += stride;
1277	}
1278
1279	return 0;
1280
1281fail:
1282	efx_siena_sriov_vfs_fini(efx);
1283	return rc;
1284}
1285
1286int efx_siena_sriov_init(struct efx_nic *efx)
1287{
1288	struct net_device *net_dev = efx->net_dev;
1289	struct siena_nic_data *nic_data = efx->nic_data;
1290	struct vfdi_status *vfdi_status;
1291	int rc;
1292
1293	/* Ensure there's room for vf_channel */
1294	BUILD_BUG_ON(EFX_MAX_CHANNELS + 1 >= EFX_VI_BASE);
1295	/* Ensure that VI_BASE is aligned on VI_SCALE */
1296	BUILD_BUG_ON(EFX_VI_BASE & ((1 << EFX_VI_SCALE_MAX) - 1));
1297
1298	if (efx->vf_count == 0)
1299		return 0;
1300
1301	rc = efx_siena_sriov_cmd(efx, true, NULL, NULL);
1302	if (rc)
1303		goto fail_cmd;
1304
1305	rc = efx_nic_alloc_buffer(efx, &nic_data->vfdi_status,
1306				  sizeof(*vfdi_status), GFP_KERNEL);
1307	if (rc)
1308		goto fail_status;
1309	vfdi_status = nic_data->vfdi_status.addr;
1310	memset(vfdi_status, 0, sizeof(*vfdi_status));
1311	vfdi_status->version = 1;
1312	vfdi_status->length = sizeof(*vfdi_status);
1313	vfdi_status->max_tx_channels = vf_max_tx_channels;
1314	vfdi_status->vi_scale = efx->vi_scale;
1315	vfdi_status->rss_rxq_count = efx->rss_spread;
1316	vfdi_status->peer_count = 1 + efx->vf_count;
1317	vfdi_status->timer_quantum_ns = efx->timer_quantum_ns;
1318
1319	rc = efx_siena_sriov_vf_alloc(efx);
1320	if (rc)
1321		goto fail_alloc;
1322
1323	mutex_init(&nic_data->local_lock);
1324	INIT_WORK(&nic_data->peer_work, efx_siena_sriov_peer_work);
1325	INIT_LIST_HEAD(&nic_data->local_addr_list);
1326	INIT_LIST_HEAD(&nic_data->local_page_list);
1327
1328	rc = efx_siena_sriov_vfs_init(efx);
1329	if (rc)
1330		goto fail_vfs;
1331
1332	rtnl_lock();
1333	ether_addr_copy(vfdi_status->peers[0].mac_addr, net_dev->dev_addr);
1334	efx->vf_init_count = efx->vf_count;
1335	rtnl_unlock();
1336
1337	efx_siena_sriov_usrev(efx, true);
1338
1339	/* At this point we must be ready to accept VFDI requests */
1340
1341	rc = pci_enable_sriov(efx->pci_dev, efx->vf_count);
1342	if (rc)
1343		goto fail_pci;
1344
1345	netif_info(efx, probe, net_dev,
1346		   "enabled SR-IOV for %d VFs, %d VI per VF\n",
1347		   efx->vf_count, efx_vf_size(efx));
1348	return 0;
1349
1350fail_pci:
1351	efx_siena_sriov_usrev(efx, false);
1352	rtnl_lock();
1353	efx->vf_init_count = 0;
1354	rtnl_unlock();
1355	efx_siena_sriov_vfs_fini(efx);
1356fail_vfs:
1357	cancel_work_sync(&nic_data->peer_work);
1358	efx_siena_sriov_free_local(efx);
1359	kfree(nic_data->vf);
1360fail_alloc:
1361	efx_nic_free_buffer(efx, &nic_data->vfdi_status);
1362fail_status:
1363	efx_siena_sriov_cmd(efx, false, NULL, NULL);
1364fail_cmd:
1365	return rc;
1366}
1367
1368void efx_siena_sriov_fini(struct efx_nic *efx)
1369{
1370	struct siena_vf *vf;
1371	unsigned int pos;
1372	struct siena_nic_data *nic_data = efx->nic_data;
1373
1374	if (efx->vf_init_count == 0)
1375		return;
1376
1377	/* Disable all interfaces to reconfiguration */
1378	BUG_ON(nic_data->vfdi_channel->enabled);
1379	efx_siena_sriov_usrev(efx, false);
1380	rtnl_lock();
1381	efx->vf_init_count = 0;
1382	rtnl_unlock();
1383
1384	/* Flush all reconfiguration work */
1385	for (pos = 0; pos < efx->vf_count; ++pos) {
1386		vf = nic_data->vf + pos;
1387		cancel_work_sync(&vf->req);
1388		cancel_work_sync(&vf->reset_work);
1389	}
1390	cancel_work_sync(&nic_data->peer_work);
1391
1392	pci_disable_sriov(efx->pci_dev);
1393
1394	/* Tear down back-end state */
1395	efx_siena_sriov_vfs_fini(efx);
1396	efx_siena_sriov_free_local(efx);
1397	kfree(nic_data->vf);
1398	efx_nic_free_buffer(efx, &nic_data->vfdi_status);
1399	efx_siena_sriov_cmd(efx, false, NULL, NULL);
1400}
1401
1402void efx_siena_sriov_event(struct efx_channel *channel, efx_qword_t *event)
1403{
1404	struct efx_nic *efx = channel->efx;
1405	struct siena_vf *vf;
1406	unsigned qid, seq, type, data;
1407
1408	qid = EFX_QWORD_FIELD(*event, FSF_CZ_USER_QID);
1409
1410	/* USR_EV_REG_VALUE is dword0, so access the VFDI_EV fields directly */
1411	BUILD_BUG_ON(FSF_CZ_USER_EV_REG_VALUE_LBN != 0);
1412	seq = EFX_QWORD_FIELD(*event, VFDI_EV_SEQ);
1413	type = EFX_QWORD_FIELD(*event, VFDI_EV_TYPE);
1414	data = EFX_QWORD_FIELD(*event, VFDI_EV_DATA);
1415
1416	netif_vdbg(efx, hw, efx->net_dev,
1417		   "USR_EV event from qid %d seq 0x%x type %d data 0x%x\n",
1418		   qid, seq, type, data);
1419
1420	if (map_vi_index(efx, qid, &vf, NULL))
1421		return;
1422	if (vf->busy)
1423		goto error;
1424
1425	if (type == VFDI_EV_TYPE_REQ_WORD0) {
1426		/* Resynchronise */
1427		vf->req_type = VFDI_EV_TYPE_REQ_WORD0;
1428		vf->req_seqno = seq + 1;
1429		vf->req_addr = 0;
1430	} else if (seq != (vf->req_seqno++ & 0xff) || type != vf->req_type)
1431		goto error;
1432
1433	switch (vf->req_type) {
1434	case VFDI_EV_TYPE_REQ_WORD0:
1435	case VFDI_EV_TYPE_REQ_WORD1:
1436	case VFDI_EV_TYPE_REQ_WORD2:
1437		vf->req_addr |= (u64)data << (vf->req_type << 4);
1438		++vf->req_type;
1439		return;
1440
1441	case VFDI_EV_TYPE_REQ_WORD3:
1442		vf->req_addr |= (u64)data << 48;
1443		vf->req_type = VFDI_EV_TYPE_REQ_WORD0;
1444		vf->busy = true;
1445		queue_work(vfdi_workqueue, &vf->req);
1446		return;
1447	}
1448
1449error:
1450	if (net_ratelimit())
1451		netif_err(efx, hw, efx->net_dev,
1452			  "ERROR: Screaming VFDI request from %s\n",
1453			  vf->pci_name);
1454	/* Reset the request and sequence number */
1455	vf->req_type = VFDI_EV_TYPE_REQ_WORD0;
1456	vf->req_seqno = seq + 1;
1457}
1458
1459void efx_siena_sriov_flr(struct efx_nic *efx, unsigned vf_i)
1460{
1461	struct siena_nic_data *nic_data = efx->nic_data;
1462	struct siena_vf *vf;
1463
1464	if (vf_i > efx->vf_init_count)
1465		return;
1466	vf = nic_data->vf + vf_i;
1467	netif_info(efx, hw, efx->net_dev,
1468		   "FLR on VF %s\n", vf->pci_name);
1469
1470	vf->status_addr = 0;
1471	efx_vfdi_remove_all_filters(vf);
1472	efx_vfdi_flush_clear(vf);
1473
1474	vf->evq0_count = 0;
1475}
1476
1477int efx_siena_sriov_mac_address_changed(struct efx_nic *efx)
1478{
1479	struct siena_nic_data *nic_data = efx->nic_data;
1480	struct vfdi_status *vfdi_status = nic_data->vfdi_status.addr;
1481
1482	if (!efx->vf_init_count)
1483		return 0;
1484	ether_addr_copy(vfdi_status->peers[0].mac_addr,
1485			efx->net_dev->dev_addr);
1486	queue_work(vfdi_workqueue, &nic_data->peer_work);
1487
1488	return 0;
1489}
1490
1491void efx_siena_sriov_tx_flush_done(struct efx_nic *efx, efx_qword_t *event)
1492{
1493	struct siena_vf *vf;
1494	unsigned queue, qid;
1495
1496	queue = EFX_QWORD_FIELD(*event,  FSF_AZ_DRIVER_EV_SUBDATA);
1497	if (map_vi_index(efx, queue, &vf, &qid))
1498		return;
1499	/* Ignore flush completions triggered by an FLR */
1500	if (!test_bit(qid, vf->txq_mask))
1501		return;
1502
1503	__clear_bit(qid, vf->txq_mask);
1504	--vf->txq_count;
1505
1506	if (efx_vfdi_flush_wake(vf))
1507		wake_up(&vf->flush_waitq);
1508}
1509
1510void efx_siena_sriov_rx_flush_done(struct efx_nic *efx, efx_qword_t *event)
1511{
1512	struct siena_vf *vf;
1513	unsigned ev_failed, queue, qid;
1514
1515	queue = EFX_QWORD_FIELD(*event, FSF_AZ_DRIVER_EV_RX_DESCQ_ID);
1516	ev_failed = EFX_QWORD_FIELD(*event,
1517				    FSF_AZ_DRIVER_EV_RX_FLUSH_FAIL);
1518	if (map_vi_index(efx, queue, &vf, &qid))
1519		return;
1520	if (!test_bit(qid, vf->rxq_mask))
1521		return;
1522
1523	if (ev_failed) {
1524		set_bit(qid, vf->rxq_retry_mask);
1525		atomic_inc(&vf->rxq_retry_count);
1526	} else {
1527		__clear_bit(qid, vf->rxq_mask);
1528		--vf->rxq_count;
1529	}
1530	if (efx_vfdi_flush_wake(vf))
1531		wake_up(&vf->flush_waitq);
1532}
1533
1534/* Called from napi. Schedule the reset work item */
1535void efx_siena_sriov_desc_fetch_err(struct efx_nic *efx, unsigned dmaq)
1536{
1537	struct siena_vf *vf;
1538	unsigned int rel;
1539
1540	if (map_vi_index(efx, dmaq, &vf, &rel))
1541		return;
1542
1543	if (net_ratelimit())
1544		netif_err(efx, hw, efx->net_dev,
1545			  "VF %d DMA Q %d reports descriptor fetch error.\n",
1546			  vf->index, rel);
1547	queue_work(vfdi_workqueue, &vf->reset_work);
1548}
1549
1550/* Reset all VFs */
1551void efx_siena_sriov_reset(struct efx_nic *efx)
1552{
1553	struct siena_nic_data *nic_data = efx->nic_data;
1554	unsigned int vf_i;
1555	struct efx_buffer buf;
1556	struct siena_vf *vf;
1557
1558	ASSERT_RTNL();
1559
1560	if (efx->vf_init_count == 0)
1561		return;
1562
1563	efx_siena_sriov_usrev(efx, true);
1564	(void)efx_siena_sriov_cmd(efx, true, NULL, NULL);
1565
1566	if (efx_nic_alloc_buffer(efx, &buf, EFX_PAGE_SIZE, GFP_NOIO))
1567		return;
1568
1569	for (vf_i = 0; vf_i < efx->vf_init_count; ++vf_i) {
1570		vf = nic_data->vf + vf_i;
1571		efx_siena_sriov_reset_vf(vf, &buf);
1572	}
1573
1574	efx_nic_free_buffer(efx, &buf);
1575}
1576
1577int efx_init_sriov(void)
1578{
1579	/* A single threaded workqueue is sufficient. efx_siena_sriov_vfdi() and
1580	 * efx_siena_sriov_peer_work() spend almost all their time sleeping for
1581	 * MCDI to complete anyway
1582	 */
1583	vfdi_workqueue = create_singlethread_workqueue("sfc_vfdi");
1584	if (!vfdi_workqueue)
1585		return -ENOMEM;
1586	return 0;
1587}
1588
1589void efx_fini_sriov(void)
1590{
1591	destroy_workqueue(vfdi_workqueue);
1592}
1593
1594int efx_siena_sriov_set_vf_mac(struct efx_nic *efx, int vf_i, u8 *mac)
1595{
1596	struct siena_nic_data *nic_data = efx->nic_data;
1597	struct siena_vf *vf;
1598
1599	if (vf_i >= efx->vf_init_count)
1600		return -EINVAL;
1601	vf = nic_data->vf + vf_i;
1602
1603	mutex_lock(&vf->status_lock);
1604	ether_addr_copy(vf->addr.mac_addr, mac);
1605	__efx_siena_sriov_update_vf_addr(vf);
1606	mutex_unlock(&vf->status_lock);
1607
1608	return 0;
1609}
1610
1611int efx_siena_sriov_set_vf_vlan(struct efx_nic *efx, int vf_i,
1612				u16 vlan, u8 qos)
1613{
1614	struct siena_nic_data *nic_data = efx->nic_data;
1615	struct siena_vf *vf;
1616	u16 tci;
1617
1618	if (vf_i >= efx->vf_init_count)
1619		return -EINVAL;
1620	vf = nic_data->vf + vf_i;
1621
1622	mutex_lock(&vf->status_lock);
1623	tci = (vlan & VLAN_VID_MASK) | ((qos & 0x7) << VLAN_PRIO_SHIFT);
1624	vf->addr.tci = htons(tci);
1625	__efx_siena_sriov_update_vf_addr(vf);
1626	mutex_unlock(&vf->status_lock);
1627
1628	return 0;
1629}
1630
1631int efx_siena_sriov_set_vf_spoofchk(struct efx_nic *efx, int vf_i,
1632				    bool spoofchk)
1633{
1634	struct siena_nic_data *nic_data = efx->nic_data;
1635	struct siena_vf *vf;
1636	int rc;
1637
1638	if (vf_i >= efx->vf_init_count)
1639		return -EINVAL;
1640	vf = nic_data->vf + vf_i;
1641
1642	mutex_lock(&vf->txq_lock);
1643	if (vf->txq_count == 0) {
1644		vf->tx_filter_mode =
1645			spoofchk ? VF_TX_FILTER_ON : VF_TX_FILTER_OFF;
1646		rc = 0;
1647	} else {
1648		/* This cannot be changed while TX queues are running */
1649		rc = -EBUSY;
1650	}
1651	mutex_unlock(&vf->txq_lock);
1652	return rc;
1653}
1654
1655int efx_siena_sriov_get_vf_config(struct efx_nic *efx, int vf_i,
1656				  struct ifla_vf_info *ivi)
1657{
1658	struct siena_nic_data *nic_data = efx->nic_data;
1659	struct siena_vf *vf;
1660	u16 tci;
1661
1662	if (vf_i >= efx->vf_init_count)
1663		return -EINVAL;
1664	vf = nic_data->vf + vf_i;
1665
1666	ivi->vf = vf_i;
1667	ether_addr_copy(ivi->mac, vf->addr.mac_addr);
1668	ivi->max_tx_rate = 0;
1669	ivi->min_tx_rate = 0;
1670	tci = ntohs(vf->addr.tci);
1671	ivi->vlan = tci & VLAN_VID_MASK;
1672	ivi->qos = (tci >> VLAN_PRIO_SHIFT) & 0x7;
1673	ivi->spoofchk = vf->tx_filter_mode == VF_TX_FILTER_ON;
1674
1675	return 0;
1676}
1677
1678bool efx_siena_sriov_wanted(struct efx_nic *efx)
1679{
1680	return efx->vf_count != 0;
1681}
1682
1683int efx_siena_sriov_configure(struct efx_nic *efx, int num_vfs)
1684{
1685	return 0;
1686}
1687